SelectionGAN icon indicating copy to clipboard operation
SelectionGAN copied to clipboard

Published 20 hours ago • verified publisher icon Ha0Tang

Checkers on generated images

Open zhangdan8962 opened this issue 4 years ago • 6 comments
trafficstars

Hi,

I have tried to duplicate the result based on your dayton_a2g_256_pretrained model. However, there are many checkers in the generated images which is not clearly shown in Fig.4 of you paper. I followed all the hyperparameters as you mentioned in readme file

I am wondering if you encountered the same issue in your experiments or do I miss anything?

The attached is one of the screenshots. Thank you in advance! Screenshot from 2021-09-06 01-18-38

zhangdan8962 avatar Sep 06 '21 05:09 zhangdan8962

The last image "I" is the final result. Are you talking about this result？

Ha0Tang avatar Sep 06 '21 08:09 Ha0Tang

My bad. I thought fake_B is the final result, which should be the result from stage1 right?

zhangdan8962 avatar Sep 06 '21 13:09 zhangdan8962

Yes, you are right.

Ha0Tang avatar Sep 06 '21 13:09 Ha0Tang

And one last question regarding the batch size. Is it simply because the cuda memory limit or is there any reasons behind the fact that you were using batch size 4?

zhangdan8962 avatar Sep 06 '21 14:09 zhangdan8962

It should be for a fair comparison with existing methods.

Ha0Tang avatar Sep 13 '21 08:09 Ha0Tang

I also realize that the fake_D is pretty blurry. Is it the output of stage 1 or 2?

zhangdan8962 avatar Nov 08 '21 03:11 zhangdan8962